Recognition information

Author

Chali, A. ; Daemi, M.F.

Author_Institution

Dept. of Comput. Sci., Nottingham Univ., UK

Volume

1

fYear

1996

fDate

25-29 Aug 1996

Firstpage

544

Abstract

This paper proposes a technique based on information theory principles for the assessment of the degree of dissimilarities between binary images. We first describe how the information content of an image may be defined, identified, assessed and analysed. This concept is then extended to the measurement of information content of more than one image. This information content measure is then shown to be related to the recognition information which is a measure of the degree of dissimilarities between images. In order to demonstrate the feasibility of the developed techniques, a series of tests were carried out on typed characters. The results illustrate the power of the information assessment techniques in analysing the recognition capabilities of a pattern recognition system

Keywords

character recognition; entropy; information theory; probability; character recognition; dissimilarity; entropy; image information content; image recognition; information theory; occurrence probability; Character recognition; Entropy; Image recognition; Image sensors; Information theory; Pattern recognition; Pixel; Sensor arrays; Shape; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.546085

Filename

546085